AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Associative Domain Adaptation

Philip Haeusser, Thomas Frerix, Alexander Mordvintsev, Daniel Cremers

ICCV 2017 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Conditional distribution alignment · 250 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add association loss to source-only traininggeneric CNN · MNIST -> MNIST-Mtarget test error (%): 35.96 -> 10.53Improved
add association loss to source-only traininggeneric CNN · Synth Digits -> SVHNtarget test error (%): 15.68 -> 8.14Improved
add association loss to source-only traininggeneric CNN · SVHN -> MNISTtarget test error (%): 30.71 -> 2.40Improved
add association loss to source-only traininggeneric CNN · Synth Signs -> GTSRBtarget test error (%): 4.59 -> 2.34Improved
use association loss instead of MMD loss as similarity term (ablation)generic CNN · MNIST -> MNIST-Mtarget test error (%): 22.90 -> 10.53Improved
use association loss instead of MMD loss as similarity term (ablation)generic CNN · Synth Digits -> SVHNtarget test error (%): 19.14 -> 8.14Improved
use association loss instead of MMD loss as similarity term (ablation)generic CNN · SVHN -> MNISTtarget test error (%): 28.48 -> 2.40Improved
use association loss instead of MMD loss as similarity term (ablation)generic CNN · Synth Signs -> GTSRBtarget test error (%): 10.69 -> 2.34Improved
add association loss on top of source-only training vs MMD loss on Synth Digits -> SVHN (ablation)generic CNN · Synth Digits -> SVHNtarget test error (%): 15.68 -> 19.14Hurt
add association loss with fixed hyperparameters on Synth Signs -> GTSRBgeneric CNN · Synth Signs -> GTSRBtarget test error (%): 4.59 -> 17.20Hurt
remove batch size constraint on traffic signs (ablation)DA_assoc fixed params · Synth Signs -> GTSRBtarget test error (%): 17.20 -> 6.55Improved
add association loss instead of MMD loss, in terms of embedding MMDgeneric CNN · SVHN -> MNISTMMD between embeddings: 0.0404 -> 0.2112Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy